© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 57554
    Prev
    Next
    INDEX
    Explanations

    know followed by question words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Antar
    -0.08
    ael
    -0.08
    едÑĮ
    -0.08
    auc
    -0.08
    nip
    -0.08
    弯
    -0.08
    巴士
    -0.08
    dam
    -0.08
     LTE
    -0.08
    bone
    -0.08
    POSITIVE LOGITS
    ä½Ĩä»İ
    0.11
    åį¤
    0.09
    ĥģ
    0.09
    formats
    0.09
    ragments
    0.08
     sonst
    0.08
    ject
    0.08
    çī¹æ®ĬæĥħåĨµ
    0.08
    çŃīçī¹çĤ¹
    0.08
    æł¹åºķ
    0.08
    Activations Density 0.038%

    No Known Activations